S. T. Boris Choy

Evaluation of nutritional and inflammatory status of advanced colorectal cancer patients and its correlation with survival.

Abstract: The purpose of this study was to evaluate novel inflammatory and nutritional prognostic factors in patients with advanced colorectal cancer (ACRC). All ACRC patients attending the clinic for palliative treatment were eligible for study. Demographics, including performance status (PS), C-reactive protein (CRP), albumin (Alb), Glasgow prognostic score (GPS), weight, weight history, body mass index (BMI), and nutritional status using the patient-generated subjective global assessment (PGSGA), were collected and correlated with survival. At a median follow-up of 29.8 mo, with a minimum follow-up of 15.7 mo, the median survival was 9.9 mo (0.8–21.8 mo). Fifteen (29%) patients were newly diagnosed (stage IV colorectal cancer), and 36 (71%) had received prior chemotherapy. Although the median BMI was 27 kg/m2 (range = 17–41 kg/m2), 28 of 50 (56%) were nutritionally at risk. In fact, 19 patients (38%) were critically in need of nutrition intervention (PGSGA score of ≥9). Thirty-three of 48 patients (69%) had an elevated CRP (>10 mg/l with a median of 21.1 mg/L), and 7 patients (15%) had both a CRP of >10 mg/l and hypoalbuminemia (< 35 g/l). A significant positive correlation was found between PGSGA score and CRP (P = 0.003; r = 0.430). Using univariate analysis, significantly worse survival was found for patients with poorer PS (P = 0.001), high GPS (P = 0.04), low Alb (P = 0.017), elevated serum alkaline phosphatase (SAP; P = 0.018), PGSGA score of > 9 (P = 0.001), and PGSGA group B/C (P = 0.02). Using the Cox proportional hazard model for multivariate survival analysis, type of treatment (hazard ratio, HR = 1.48; 95% confidence interval, CI = 1.11–1.79; P = 0.005), PS (HR = 2.37; 95% CI = 1.11–5.09; P = 0.026), GPS (HR = 2.27; 95% CI = 1.09–4.73; P = 0.028), and SAP (HR = 0.44; 95% CI = 0.18–1.07; P =0.069) remained significant predictors of survival. These preliminary data suggest that the type of treatment, PS, GPS, and SAP are important predictors of survival in ACRC.

Nutritional Assessment in Cancer: Comparing the Mini-Nutritional Assessment (MNA) With the Scored Patient-Generated Subjective Global Assessment (PGSGA)

Abstract: The evaluation of nutritional status in cancer patients is often neglected in spite of the fact that poor nutritional status may adversely affect prognosis and treatment tolerance. In day-to-day oncology practice, a sensitive but simply applied nutritional assessment tool is needed to identify at-risk patients. Several tools exist; however, none has been universally accepted. The aim of this study was to compare two potential tools, the Mini-Nutritional Assessment (MNA) and the scored Patient Generated Subjective Global Assessment (PGSGA). The MNA is more simply applied and does not require a trained dietitian. The PGSGA has been previously validated in cancer patients. One hundred fifty-seven newly diagnosed cancer patients were assessed using both tools. Of these, 126 were reassessed at 4-6 wk, and 104 were reassessed at Weeks 8-12 after initial assessment. A significant negative correlation was found between the tools at all three time periods (at baseline r = -0.76; P < 0.001). Taking the PGSGA as the most accepted nutritional assessment tool, at baseline the MNA demonstrated a sensitivity of 97% and specificity of 54%. At 4-6 wk MNA sensitivity was 79% and specificity was 69%. At 8-12 wk MNA sensitivity was 93% and specificity was 82%. When comparing the tools in elderly patients alone (>65 yr), similar results were obtained. Both tools were able to correctly classify patients as malnourished, although the MNA lacks specificity. Therefore, the PGSGA should be the tool of choice for nutritional assessment in cancer patients.

Altered motor control, posture and the Pilates method of exercise prescription

The objectives of this study were to compare the effects of three different Pilates regimes on chronic, mild low back pain symptoms and to determine whether the efficiency of load transfer through the pelvis is improved by those exercises. A between subjects equivalent group experimental design was used. The independent variable was the type of exercise training (three groups) and the two-dependent variables were low back pain symptoms and load transfer through the pelvis. The outcome measures of the first-dependent variable were a comparison between modified Oswestry Disability Questionnaires (one of the standard pain instruments) completed pre- and post-program and frequency, intensity and duration of low back pain. The outcome measure of the second-dependent variable, efficiency of load transfer through the pelvis was the Stork test (one-legged standing test) in weight bearing. Although all groups experienced statistically significant reductions in frequency, intensity and duration of low back pain across the weeks of exercising, there were no significant differences between the groups relative to each other.

Stochastic volatility models with leverage and heavy-tailed distributions: A Bayesian approach using scale mixtures

This paper studies a heavy-tailed stochastic volatility (SV) model with leverage effect, where a bivariate Student-t distribution is used to model the error innovations of the return and volatility equations. Choy et al. (2008) studied this model by expressing the bivariate Student-t distribution as a scale mixture of bivariate normal distributions. We propose an alternative formulation by first deriving a conditional Student-t distribution for the return and a marginal Student-t distribution for the log-volatility and then express these two Student-t distributions as a scale mixture of normal (SMN) distributions. Our approach separates the sources of outliers and allows for distinguishing between outliers generated by the return process or by the volatility process, and hence is an improvement over the approach of Choy et al. (2008). In addition, it allows an efficient model implementation using the WinBUGS software. A simulation study is conducted to assess the performance of the proposed approach and its comparison with the approach by Choy et al. (2008). In the empirical study, daily exchange rate returns of the Australian dollar to various currencies and daily stock market index returns of various international stock markets are analysed. Model comparison relies on the Deviance Information Criterion and convergence diagnostic is monitored by Gewekes convergence test.

An evaluation of the prevalence of malnutrition in cancer patients attending the outpatient oncology clinic

Background:  The aim of the study was to assess the nutritional status of cancer patients attending the medical oncology outpatient setting for the first time.

Modelling stochastic volatility using generalized t distribution

In modelling financial return time series and time-varying volatility, the Gaussian and the Student-t distributions are widely used in stochastic volatility (SV) models. However, other distributions such as the Laplace distribution and generalized error distribution (GED) are also common in SV modelling. Therefore, this paper proposes the use of the generalized t (GT) distribution whose special cases are the Gaussian distribution, Student-t distribution, Laplace distribution and GED. Since the GT distribution is a member of the scale mixture of uniform (SMU) family of distribution, we handle the GT distribution via its SMU representation. We show this SMU form can substantially simplify the Gibbs sampler for Bayesian simulation-based computation and can provide a mean of identifying outliers. In an empirical study, we adopt a GT–SV model to fit the daily return of the exchange rate of Australian dollar to three other currencies and use the exchange rate to US dollar as a covariate. Model implementation relies on Bayesian Markov chain Monte Carlo algorithms using the WinBUGS package.

SCALE MIXTURES DISTRIBUTIONS IN INSURANCE APPLICATIONS

In this paper non-normal distributions via scale mixtures are introduced into insurance applications. The symmetric distributions of interest are the Studentt and exponential power (EP) distributions. A Bayesian approach is adopted with the aid of simulation to obtain posterior summaries. We shall show that the computational burden for the Bayesian calculations is alleviated via the scale mixtures representations. Illustrative examples are given.

Bayesian student-t

The normal error distribution for the observations and log-volatilities in a stochastic volatility (SV) model is replaced by the Student-t distribution for robustness consideration. The model is then called the t-t SV model throughout this paper. The objectives of the paper are twofold. First, we introduce the scale mixtures of uniform (SMU) and the scale mixtures of normal (SMN) representations to the Student-t density and show that the setup of a Gibbs sampler for the t-t SV model can be simplified. For example, the full conditional distribution of the log-volatilities has a truncated normal distribution that enables an efficient Gibbs sampling algorithm. These representations also provide a means for outlier diagnostics. Second, we consider the so-called t SV model with leverage where the observations and log-volatilities follow a bivariate t distribution. Returns on exchange rates of Australian dollar to 10 major currencies are fitted by the t-t SV model and the t SV model with leverage, respectively.

Nonignorable dropout models for longitudinal binary data with random effects: An application of Monte Carlo approximation through the Gibbs output

The analysis of longitudinal data with nonignorable dropout remains an active area in biostatistics research. Nonignorable dropout (ND) refers to the type of dropout when the probability of dropout depends on the missing observations at or after the time of dropout. Failure to account for such dependence may result in biased inference. Motivated by a methadone clinic data of longitudinal binary observations with dropouts, we propose a conditional first order autoregressive (AR1) logit model for the outcome measurements. The model is further extended to incorporate random effects in order to account for the population heterogeneity and intra-cluster correlation. The purposed models account for the dropout mechanism by a separate logit model in some covariates and missing outcomes for the binary dropout indicators. For model implementation, we proposed a likelihood approach through Monte Carlo approximation to the Gibbs output that evaluates the complicated likelihood function for the random effect ND model without tear. Finally simulation studies are performed to evaluate the biases on the parameter estimates of the outcome model for different dropout mechanisms.

Bivariate asymmetric GARCH models with heavy tails and dynamic conditional correlations

A bivariate generalized autoregressive conditional heteroskedastic model with dynamic conditional correlation and leverage effect (DCC-GJR-GARCH) for modelling financial time series data is considered. For robustness it is helpful to assume a multivariate Student-t distribution for the innovation terms. This paper proposes a new modified multivariate t-distribution which is a robustifying distribution and offers independent marginal Student-t distributions with different degrees of freedom, thereby highlighting the relationship among different assets. A Bayesian approach with adaptive Markov chain Monte Carlo methods is used for statistical inference. A simulation experiment illustrates good performance in estimation over reasonable sample sizes. In the empirical studies, the pairwise relationship between the Australian stock market and foreign exchange market, and between the US stock market and crude oil market are investigated, including out-of-sample volatility forecasts.